Create app.py

app.py

@@ -0,0 +1,102 @@
+import gradio as gr
+import fitz  # PyMuPDF for PDF extraction
+from huggingface_hub import InferenceClient
+import os
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_path):
+    try:
+        doc = fitz.open(pdf_path)
+        text = ""
+        for page in doc:
+            text += page.get_text()
+        return text
+    except Exception as e:
+        print(f"Error extracting text from PDF: {str(e)}")
+        return None
+
+# Function to send extracted text to the model and get the details
+def extract_invoice_details_from_text(text, prompt, model_name, api_key):
+    try:
+        # Initialize the InferenceClient with the provided API key
+        client = InferenceClient(api_key=api_key)
+
+        # Send prompt to the selected model
+        response = client.chat.completions.create(
+            model=model_name,  # Use the model selected by the user
+            messages=[{"role": "user", "content": prompt + text}],  # Append extracted PDF text to prompt
+            max_tokens=2000  # Adjust token size as needed
+        )
+        # Ensure the response format is correct and extract the content
+        return response['choices'][0]['message']['content']
+    except Exception as e:
+        print(f"Error occurred while processing the request: {str(e)}")
+        return "Error occurred while processing the request."
+
+# Main function to process PDFs
+def process_files(files, prompt, model_name, api_key):
+    if not api_key.strip():
+        return "Please provide a valid Hugging Face API key."
+
+    default_prompt = (
+        "Can you please parse below details from attached documents in excel format?\n"
+        "information to extract: DATE, NAME & ADDRESS OF BUYER, Item Code, HSN CODE, UOM, Qty, Unit Price\n\nInvoice text:\n"
+    )
+    user_prompt = prompt.strip() if prompt.strip() else default_prompt
+    all_extracted_data = []
+
+    for file in files:
+        try:
+            pdf_text = extract_text_from_pdf(file.name)
+            if not pdf_text:
+                all_extracted_data.append(f"Failed to extract text from {file.name}")
+                continue
+
+            # Get details from the model based on extracted text and the provided prompt
+            extracted_text = extract_invoice_details_from_text(pdf_text, user_prompt, model_name, api_key)
+            all_extracted_data.append(f"File: {file.name}\n{extracted_text.strip()}")
+        except Exception as e:
+            print(f"Error processing file {file.name}: {str(e)}")
+            all_extracted_data.append(f"Error processing {file.name}: {str(e)}")
+
+    return "\n\n".join(all_extracted_data)
+
+# Define the Gradio app interface
+with gr.Blocks() as app:
+    gr.Markdown("# Information Parser App")
+    gr.Markdown("Upload PDF with text, provide a prompt, your Hugging Face API key, and select a model to extract details.")
+
+    with gr.Row():
+        file_input = gr.File(label="Upload PDF(s)", file_types=[".pdf"], file_count="multiple")
+        model_dropdown = gr.Dropdown(
+            label="Select Model",
+            choices=["Qwen/Qwen2.5-Coder-32B-Instruct", "gpt-3.5-turbo", "other-model-name"],
+            value="Qwen/Qwen2.5-Coder-32B-Instruct"
+        )
+    prompt_input = gr.Textbox(
+        label="Custom Prompt",
+        placeholder="Enter your custom prompt here (leave blank to use default prompt).",
+        lines=3
+    )
+    api_key_input = gr.Textbox(
+        label="Hugging Face API Key",
+        placeholder="Enter your Hugging Face API key here.",
+        type="password",
+        lines=1
+    )
+    extract_button = gr.Button("Extract Details from PDF")
+    output_box = gr.Textbox(
+        label="Extracted Data",
+        placeholder="The extracted details will appear here.",
+        lines=15,
+        interactive=False
+    )
+
+    extract_button.click(
+        process_files,
+        inputs=[file_input, prompt_input, model_dropdown, api_key_input],
+        outputs=output_box
+    )
+
+# Launch the app
+app.launch()